G4 CUT&Tag analysis mESC (WT, FANCJ KO, DHX36 KO, DKO)

Simon Elsässer, Karolinska Institutet (2023)

Profile plots of promoters, enhancders and significant peaks determined by DESeq2.

bw_dir <- "/Volumes/DATA/DATA/Puck/bigwig/"

library("wigglescout")
library("ggpubr")

Loading required package: ggplot2

library("ggplot2")
library("DESeq2")

Loading required package: S4Vectors
Warning: package ‘S4Vectors’ was built under R version 4.2.2Loading required package: stats4
Loading required package: BiocGenerics

Attaching package: ‘BiocGenerics’

The following objects are masked from ‘package:stats’:

    IQR, mad, sd, var, xtabs

The following objects are masked from ‘package:base’:

    anyDuplicated, aperm, append, as.data.frame, basename, cbind, colnames,
    dirname, do.call, duplicated, eval, evalq, Filter, Find, get, grep, grepl,
    intersect, is.unsorted, lapply, Map, mapply, match, mget, order, paste, pmax,
    pmax.int, pmin, pmin.int, Position, rank, rbind, Reduce, rownames, sapply,
    setdiff, sort, table, tapply, union, unique, unsplit, which.max, which.min


Attaching package: ‘S4Vectors’

The following objects are masked from ‘package:base’:

    expand.grid, I, unname

Loading required package: IRanges
Loading required package: GenomicRanges
Warning: package ‘GenomicRanges’ was built under R version 4.2.2Loading required package: GenomeInfoDb
Warning: package ‘GenomeInfoDb’ was built under R version 4.2.2Loading required package: SummarizedExperiment
Loading required package: MatrixGenerics
Loading required package: matrixStats

Attaching package: ‘MatrixGenerics’

The following objects are masked from ‘package:matrixStats’:

    colAlls, colAnyNAs, colAnys, colAvgsPerRowSet, colCollapse, colCounts,
    colCummaxs, colCummins, colCumprods, colCumsums, colDiffs, colIQRDiffs,
    colIQRs, colLogSumExps, colMadDiffs, colMads, colMaxs, colMeans2, colMedians,
    colMins, colOrderStats, colProds, colQuantiles, colRanges, colRanks,
    colSdDiffs, colSds, colSums2, colTabulates, colVarDiffs, colVars,
    colWeightedMads, colWeightedMeans, colWeightedMedians, colWeightedSds,
    colWeightedVars, rowAlls, rowAnyNAs, rowAnys, rowAvgsPerColSet, rowCollapse,
    rowCounts, rowCummaxs, rowCummins, rowCumprods, rowCumsums, rowDiffs,
    rowIQRDiffs, rowIQRs, rowLogSumExps, rowMadDiffs, rowMads, rowMaxs, rowMeans2,
    rowMedians, rowMins, rowOrderStats, rowProds, rowQuantiles, rowRanges,
    rowRanks, rowSdDiffs, rowSds, rowSums2, rowTabulates, rowVarDiffs, rowVars,
    rowWeightedMads, rowWeightedMeans, rowWeightedMedians, rowWeightedSds,
    rowWeightedVars

Loading required package: Biobase
Welcome to Bioconductor

    Vignettes contain introductory material; view with 'browseVignettes()'. To
    cite Bioconductor, see 'citation("Biobase")', and for packages
    'citation("pkgname")'.


Attaching package: ‘Biobase’

The following object is masked from ‘package:MatrixGenerics’:

    rowMedians

The following objects are masked from ‘package:matrixStats’:

    anyMissing, rowMedians

library("dplyr")

Attaching package: ‘dplyr’

The following object is masked from ‘package:Biobase’:

    combine

The following object is masked from ‘package:matrixStats’:

    count

The following objects are masked from ‘package:GenomicRanges’:

    intersect, setdiff, union

The following object is masked from ‘package:GenomeInfoDb’:

    intersect

The following objects are masked from ‘package:IRanges’:

    collapse, desc, intersect, setdiff, slice, union

The following objects are masked from ‘package:S4Vectors’:

    first, intersect, rename, setdiff, setequal, union

The following objects are masked from ‘package:BiocGenerics’:

    combine, intersect, setdiff, union

The following objects are masked from ‘package:stats’:

    filter, lag

The following objects are masked from ‘package:base’:

    intersect, setdiff, setequal, union

library("ggrastr")

clean <- function (fn) {
  fn <- gsub(pattern = ".+/", "", x = fn)
  fn <- gsub(pattern = ".mm9.+", "", x = fn)
  fn <- gsub(pattern = ".mm39.+", "", x = fn)
  fn <- gsub(pattern = "_S.+", "", x = fn)
  fn <- gsub(pattern = "_combined.+", "", x = fn)
  fn <- gsub(pattern = "G4 CnT ", "", x = fn)
  fn <- gsub(pattern = "_batch2", "", x = fn)
  fn <- gsub(pattern = "-", " ", x = fn)
  fn <- gsub(pattern = "_", " ", x = fn)
  fn <- gsub(pattern = " HA ", " ", x = fn)
  fn <- gsub(pattern = "D1D6", "FANCJ-/-", x = fn)
  fn <- gsub(pattern = "P2D2", "DHX36-/-", x = fn)
  fn <- gsub(pattern = "P3D4", "FANCJ-/-DHX36-/-", x = fn)
  return(fn)
}

BWs <- paste0(bw_dir,list.files(bw_dir,pattern="G4_.+_combined.bw"))

mypal <-c("cornflowerblue","orange","red2","#505050")
mypal3 <-c("cornflowerblue","cornflowerblue","cornflowerblue","orange","orange","orange","red2","red","red2","black","black","black")
mypal2 <-c("cornflowerblue","cornflowerblue","orange","orange","red2","red","black","black")

DHX36-/- vs WT significant peaks

FANCJ-/- vs WT significant peaks

DKO-/- vs WT significant peaks

DKO-/- vs WT significant peaks

MACS peak intersect not called in WT

#non-significant Peaks

Active Promoters

Active Enhancers

ggsave("plots/profile_G4_DHX36.pdf",plot_profile_G4_DHX36,width = 3, height= 3)
ggsave("plots/profile_G4_FANCJ.pdf",plot_profile_G4_FANCJ,width = 3, height= 3)
ggsave("plots/profile_G4_DKO.pdf",plot_profile_G4_DKO,width = 3, height= 3)
ggsave("plots/profile_G4_nonsig.pdf",plot_profile_G4_nonsig,width = 3, height= 3)
ggsave("plots/profile_G4_ProAct.pdf",plot_profile_G4_proact,width = 3, height= 3)

Error in plot_theme(plot) : object 'plot_profile_G4_proact' not found

Heatmaps

ggsave("panels/heatmap_G4.pdf",plot_heatmap_G4,width = 6, height= 3)

library(cowplot)

Attaching package: ‘cowplot’

The following object is masked from ‘package:ggpubr’:

    get_legend

p <- ggdraw() +
  draw_plot(plot_profile_G4_DHX36, x = 0, y = 0, width = .33, height = 1) +
  draw_plot(plot_profile_G4_nonsig, x = .33, y = 0, width = .33, height = 1) +
  draw_plot(plot_profile_G4_enhact, x = 0.66, y = 0, width = .33, height = 1)
p

ggsave("panels/profiles_G4_peak_enh.pdf",p,width=8, height=3)

p <- ggdraw() +
  draw_plot(plot_heatmap_G4, x = .0, y = 0, width = .5, height = 1) +
  draw_plot(plot_profile_G4_DHX36, x = .5, y = 0.5, width = .25, height = .5) +
  draw_plot(plot_profile_G4_FANCJ, x = .5, y = 0, width = .25, height = .5) +
  draw_plot(plot_profile_G4_DKO, x = .75, y = 0.5, width = .25, height = .5) +
  draw_plot(plot_profile_G4_nonsig, x = 0.75, y = 0, width = .25, height = .5)
p

ggsave("panels/heatmap_G4_peaks.pdf",p,width=10, height=5)

p <- ggdraw() +
  draw_plot(plot_heatmap_G4, x = .0, y = 0, width = .5, height = 1) +
  draw_plot(plot_profile_G4_DKO, x = .5, y = 0.5, width = .25, height = .5) +
  draw_plot(plot_profile_G4_nonsig, x = .5, y = 0, width = .25, height = .5) +
  draw_plot(plot_profile_G4_proact, x = .75, y = 0.5, width = .25, height = .5) +
  draw_plot(plot_profile_G4_enhact, x = 0.75, y = 0, width = .25, height = .5)
p

ggsave("panels/heatmap_G4_peaks_pro_enh.pdf",p,width=10, height=5)

R loops

ggsave("plots/profile_Rloop_DHX36.pdf",plot_profile_Rloop_DHX36,width = 3, height= 3)
ggsave("plots/profile_Rloop_FANCJ.pdf",plot_profile_Rloop_FANCJ,width = 3, height= 3)
ggsave("plots/profile_Rloop_DKO.pdf",plot_profile_Rloop_DKO,width = 3, height= 3)
ggsave("plots/profile_Rloop_nonsig.pdf",plot_profile_Rloop_nonsig,width = 3, height= 3)

p <- ggdraw() +
  draw_plot(plot_heatmap_Rloop, x = .0, y = 0, width = .5, height = 1) +
  draw_plot(plot_profile_Rloop_DHX36, x = .5, y = 0.5, width = .25, height = .5) +
  draw_plot(plot_profile_Rloop_FANCJ, x = .5, y = 0, width = .25, height = .5) +
  draw_plot(plot_profile_Rloop_DKO, x = .75, y = 0.5, width = .25, height = .5) +
  draw_plot(plot_profile_Rloop_nonsig, x = 0.75, y = 0, width = .25, height = .5)
p

ggsave("panels/peak_Rloop_heatmap.pdf",p,width=10, height=5)

p <- ggdraw() +
  draw_plot(plot_profile_Rloop_DHX36, x = 0, y = 0, width = .33, height = 1) +
  draw_plot(plot_profile_Rloop_DKO, x = .33, y = 0, width = .33, height = 1) +
  draw_plot(plot_profile_Rloop_nonsig, x = 0.66, y = 0, width = .33, height = 1)
p

ggsave("panels/peak_Rloop_profiles.pdf",p,width=8, height=3)

mdf <- melt(df)

ggviolin(mdf, x="variable",y="value",fill="variable",palette = mypal, add="mean_sd") +
  coord_cartesian(ylim=c(0,15))